Hybrid Dialog State Tracker
This work addresses dialog state tracking for conversational AI systems, presenting an incremental improvement.
The paper tackles dialog state tracking by combining rule-based and LSTM-based machine learning approaches, achieving a new state-of-the-art result on the DSTC 2 dataset with live SLU input.
This paper presents a hybrid dialog state tracker that combines a rule based and a machine learning based approach to belief state tracking. Therefore, we call it a hybrid tracker. The machine learning in our tracker is realized by a Long Short Term Memory (LSTM) network. To our knowledge, our hybrid tracker sets a new state-of-the-art result for the Dialog State Tracking Challenge (DSTC) 2 dataset when the system uses only live SLU as its input.